summaryrefslogtreecommitdiffstats
path: root/mm/mmu_gather.c
blob: 99b3e9408aa0fb8961c980fe7cf18162fde1d427 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
#include <linux/gfp.h>
#include <linux/highmem.h>
#include <linux/kernel.h>
#include <linux/mmdebug.h>
#include <linux/mm_types.h>
#include <linux/mm_inline.h>
#include <linux/pagemap.h>
#include <linux/rcupdate.h>
#include <linux/smp.h>
#include <linux/swap.h>
#include <linux/rmap.h>

#include <asm/pgalloc.h>
#include <asm/tlb.h>

#ifndef CONFIG_MMU_GATHER_NO_GATHER

static bool tlb_next_batch(struct mmu_gather *tlb)
{
	struct mmu_gather_batch *batch;

	/* Limit batching if we have delayed rmaps pending */
	if (tlb->delayed_rmap && tlb->active != &tlb->local)
		return false;

	batch = tlb->active;
	if (batch->next) {
		tlb->active = batch->next;
		return true;
	}

	if (tlb->batch_count == MAX_GATHER_BATCH_COUNT)
		return false;

	batch = (void *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
	if (!batch)
		return false;

	tlb->batch_count++;
	batch->next = NULL;
	batch->nr   = 0;
	batch->max  = MAX_GATHER_BATCH;

	tlb->active->next = batch;
	tlb->active = batch;

	return true;
}

#ifdef CONFIG_SMP
static void tlb_flush_rmap_batch(struct mmu_gather_batch *batch, struct vm_area_struct *vma)
{
	struct encoded_page **pages = batch->encoded_pages;

	for (int i = 0; i < batch->nr; i++) {
		struct encoded_page *enc = pages[i];

		if (encoded_page_flags(enc) & ENCODED_PAGE_BIT_DELAY_RMAP) {
			struct page *page = encoded_page_ptr(enc);
			unsigned int nr_pages = 1;

			if (unlikely(encoded_page_flags(enc) &
				     ENCODED_PAGE_BIT_NR_PAGES_NEXT))
				nr_pages = encoded_nr_pages(pages[++i]);

			folio_remove_rmap_ptes(page_folio(page), page, nr_pages,
					       vma);
		}
	}
}

/**
 * tlb_flush_rmaps - do pending rmap removals after we have flushed the TLB
 * @tlb: the current mmu_gather
 * @vma: The memory area from which the pages are being removed.
 *
 * Note that because of how tlb_next_batch() above works, we will
 * never start multiple new batches with pending delayed rmaps, so
 * we only need to walk through the current active batch and the
 * original local one.
 */
void tlb_flush_rmaps(struct mmu_gather *tlb, struct vm_area_struct *vma)
{
	if (!tlb->delayed_rmap)
		return;

	tlb_flush_rmap_batch(&tlb->local, vma);
	if (tlb->active != &tlb->local)
		tlb_flush_rmap_batch(tlb->active, vma);
	tlb->delayed_rmap = 0;
}
#endif

/*
 * We might end up freeing a lot of pages. Reschedule on a regular
 * basis to avoid soft lockups in configurations without full
 * preemption enabled. The magic number of 512 folios seems to work.
 */
#define MAX_NR_FOLIOS_PER_FREE		512

static void __tlb_batch_free_encoded_pages(struct mmu_gather_batch *batch)
{
	struct encoded_page **pages = batch->encoded_pages;
	unsigned int nr, nr_pages;

	while (batch->nr) {
		if (!page_poisoning_enabled_static() && !want_init_on_free()) {
			nr = min(MAX_NR_FOLIOS_PER_FREE, batch->nr);

			/*
			 * Make sure we cover page + nr_pages, and don't leave
			 * nr_pages behind when capping the number of entries.
			 */
			if (unlikely(encoded_page_flags(pages[nr - 1]) &
				     ENCODED_PAGE_BIT_NR_PAGES_NEXT))
				nr++;
		} else {
			/*
			 * With page poisoning and init_on_free, the time it
			 * takes to free memory grows proportionally with the
			 * actual memory size. Therefore, limit based on the
			 * actual memory size and not the number of involved
			 * folios.
			 */
			for (nr = 0, nr_pages = 0;
			     nr < batch->nr && nr_pages < MAX_NR_FOLIOS_PER_FREE;
			     nr++) {
				if (unlikely(encoded_page_flags(pages[nr]) &
					     ENCODED_PAGE_BIT_NR_PAGES_NEXT))
					nr_pages += encoded_nr_pages(pages[++nr]);
				else
					nr_pages++;
			}
		}

		free_pages_and_swap_cache(pages, nr);
		pages += nr;
		batch->nr -= nr;

		cond_resched();
	}
}

static void tlb_batch_pages_flush(struct mmu_gather *tlb)
{
	struct mmu_gather_batch *batch;

	for (batch = &tlb->local; batch && batch->nr; batch = batch->next)
		__tlb_batch_free_encoded_pages(batch);
	tlb->active = &tlb->local;
}

static void tlb_batch_list_free(struct mmu_gather *tlb)
{
	struct mmu_gather_batch *batch, *next;

	for (batch = tlb->local.next; batch; batch = next) {
		next = batch->next;
		free_pages((unsigned long)batch, 0);
	}
	tlb->local.next = NULL;
}

static bool __tlb_remove_folio_pages_size(struct mmu_gather *tlb,
		struct page *page, unsigned int nr_pages, bool delay_rmap,
		int page_size)
{
	int flags = delay_rmap ? ENCODED_PAGE_BIT_DELAY_RMAP : 0;
	struct mmu_gather_batch *batch;

	VM_BUG_ON(!tlb->end);

#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
	VM_WARN_ON(tlb->page_size != page_size);
	VM_WARN_ON_ONCE(nr_pages != 1 && page_size != PAGE_SIZE);
	VM_WARN_ON_ONCE(page_folio(page) != page_folio(page + nr_pages - 1));
#endif

	batch = tlb->active;
	/*
	 * Add the page and check if we are full. If so
	 * force a flush.
	 */
	if (likely(nr_pages == 1)) {
		batch->encoded_pages[batch->nr++] = encode_page(page, flags);
	} else {
		flags |= ENCODED_PAGE_BIT_NR_PAGES_NEXT;
		batch->encoded_pages[batch->nr++] = encode_page(page, flags);
		batch->encoded_pages[batch->nr++] = encode_nr_pages(nr_pages);
	}
	/*
	 * Make sure that we can always add another "page" + "nr_pages",
	 * requiring two entries instead of only a single one.
	 */
	if (batch->nr >= batch->max - 1) {
		if (!tlb_next_batch(tlb))
			return true;
		batch = tlb->active;
	}
	VM_BUG_ON_PAGE(batch->nr > batch->max - 1, page);

	return false;
}

bool __tlb_remove_folio_pages(struct mmu_gather *tlb, struct page *page,
		unsigned int nr_pages, bool delay_rmap)
{
	return __tlb_remove_folio_pages_size(tlb, page, nr_pages, delay_rmap,
					     PAGE_SIZE);
}

bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page,
		bool delay_rmap, int page_size)
{
	return __tlb_remove_folio_pages_size(tlb, page, 1, delay_rmap, page_size);
}

#endif /* MMU_GATHER_NO_GATHER */

#ifdef CONFIG_MMU_GATHER_TABLE_FREE

static void __tlb_remove_table_free(struct mmu_table_batch *batch)
{
	int i;

	for (i = 0; i < batch->nr; i++)
		__tlb_remove_table(batch->tables[i]);

	free_page((unsigned long)batch);
}

#ifdef CONFIG_MMU_GATHER_RCU_TABLE_FREE

/*
 * Semi RCU freeing of the page directories.
 *
 * This is needed by some architectures to implement software pagetable walkers.
 *
 * gup_fast() and other software pagetable walkers do a lockless page-table
 * walk and therefore needs some synchronization with the freeing of the page
 * directories. The chosen means to accomplish that is by disabling IRQs over
 * the walk.
 *
 * Architectures that use IPIs to flush TLBs will then automagically DTRT,
 * since we unlink the page, flush TLBs, free the page. Since the disabling of
 * IRQs delays the completion of the TLB flush we can never observe an already
 * freed page.
 *
 * Architectures that do not have this (PPC) need to delay the freeing by some
 * other means, this is that means.
 *
 * What we do is batch the freed directory pages (tables) and RCU free them.
 * We use the sched RCU variant, as that guarantees that IRQ/preempt disabling
 * holds off grace periods.
 *
 * However, in order to batch these pages we need to allocate storage, this
 * allocation is deep inside the MM code and can thus easily fail on memory
 * pressure. To guarantee progress we fall back to single table freeing, see
 * the implementation of tlb_remove_table_one().
 *
 */

static void tlb_remove_table_smp_sync(void *arg)
{
	/* Simply deliver the interrupt */
}

void tlb_remove_table_sync_one(void)
{
	/*
	 * This isn't an RCU grace period and hence the page-tables cannot be
	 * assumed to be actually RCU-freed.
	 *
	 * It is however sufficient for software page-table walkers that rely on
	 * IRQ disabling.
	 */
	smp_call_function(tlb_remove_table_smp_sync, NULL, 1);
}

static void tlb_remove_table_rcu(struct rcu_head *head)
{
	__tlb_remove_table_free(container_of(head, struct mmu_table_batch, rcu));
}

static void tlb_remove_table_free(struct mmu_table_batch *batch)
{
	call_rcu(&batch->rcu, tlb_remove_table_rcu);
}

#else /* !CONFIG_MMU_GATHER_RCU_TABLE_FREE */

static void tlb_remove_table_free(struct mmu_table_batch *batch)
{
	__tlb_remove_table_free(batch);
}

#endif /* CONFIG_MMU_GATHER_RCU_TABLE_FREE */

/*
 * If we want tlb_remove_table() to imply TLB invalidates.
 */
static inline void tlb_table_invalidate(struct mmu_gather *tlb)
{
	if (tlb_needs_table_invalidate()) {
		/*
		 * Invalidate page-table caches used by hardware walkers. Then
		 * we still need to RCU-sched wait while freeing the pages
		 * because software walkers can still be in-flight.
		 */
		tlb_flush_mmu_tlbonly(tlb);
	}
}

static void tlb_remove_table_one(void *table)
{
	tlb_remove_table_sync_one();
	__tlb_remove_table(table);
}

static void tlb_table_flush(struct mmu_gather *tlb)
{
	struct mmu_table_batch **batch = &tlb->batch;

	if (*batch) {
		tlb_table_invalidate(tlb);
		tlb_remove_table_free(*batch);
		*batch = NULL;
	}
}

void tlb_remove_table(struct mmu_gather *tlb, void *table)
{
	struct mmu_table_batch **batch = &tlb->batch;

	if (*batch == NULL) {
		*batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN);
		if (*batch == NULL) {
			tlb_table_invalidate(tlb);
			tlb_remove_table_one(table);
			return;
		}
		(*batch)->nr = 0;
	}

	(*batch)->tables[(*batch)->nr++] = table;
	if ((*batch)->nr == MAX_TABLE_BATCH)
		tlb_table_flush(tlb);
}

static inline void tlb_table_init(struct mmu_gather *tlb)
{
	tlb->batch = NULL;
}

#else /* !CONFIG_MMU_GATHER_TABLE_FREE */

static inline void tlb_table_flush(struct mmu_gather *tlb) { }
static inline void tlb_table_init(struct mmu_gather *tlb) { }

#endif /* CONFIG_MMU_GATHER_TABLE_FREE */

static void tlb_flush_mmu_free(struct mmu_gather *tlb)
{
	tlb_table_flush(tlb);
#ifndef CONFIG_MMU_GATHER_NO_GATHER
	tlb_batch_pages_flush(tlb);
#endif
}

void tlb_flush_mmu(struct mmu_gather *tlb)
{
	tlb_flush_mmu_tlbonly(tlb);
	tlb_flush_mmu_free(tlb);
}

static void __tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
			     bool fullmm)
{
	tlb->mm = mm;
	tlb->fullmm = fullmm;

#ifndef CONFIG_MMU_GATHER_NO_GATHER
	tlb->need_flush_all = 0;
	tlb->local.next = NULL;
	tlb->local.nr   = 0;
	tlb->local.max  = ARRAY_SIZE(tlb->__pages);
	tlb->active     = &tlb->local;
	tlb->batch_count = 0;
#endif
	tlb->delayed_rmap = 0;

	tlb_table_init(tlb);
#ifdef CONFIG_MMU_GATHER_PAGE_SIZE
	tlb->page_size = 0;
#endif

	__tlb_reset_range(tlb);
	inc_tlb_flush_pending(tlb->mm);
}

/**
 * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down
 * @tlb: the mmu_gather structure to initialize
 * @mm: the mm_struct of the target address space
 *
 * Called to initialize an (on-stack) mmu_gather structure for page-table
 * tear-down from @mm.
 */
void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm)
{
	__tlb_gather_mmu(tlb, mm, false);
}

/**
 * tlb_gather_mmu_fullmm - initialize an mmu_gather structure for page-table tear-down
 * @tlb: the mmu_gather structure to initialize
 * @mm: the mm_struct of the target address space
 *
 * In this case, @mm is without users and we're going to destroy the
 * full address space (exit/execve).
 *
 * Called to initialize an (on-stack) mmu_gather structure for page-table
 * tear-down from @mm.
 */
void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm)
{
	__tlb_gather_mmu(tlb, mm, true);
}

/**
 * tlb_finish_mmu - finish an mmu_gather structure
 * @tlb: the mmu_gather structure to finish
 *
 * Called at the end of the shootdown operation to free up any resources that
 * were required.
 */
void tlb_finish_mmu(struct mmu_gather *tlb)
{
	/*
	 * If there are parallel threads are doing PTE changes on same range
	 * under non-exclusive lock (e.g., mmap_lock read-side) but defer TLB
	 * flush by batching, one thread may end up seeing inconsistent PTEs
	 * and result in having stale TLB entries.  So flush TLB forcefully
	 * if we detect parallel PTE batching threads.
	 *
	 * However, some syscalls, e.g. munmap(), may free page tables, this
	 * needs force flush everything in the given range. Otherwise this
	 * may result in having stale TLB entries for some architectures,
	 * e.g. aarch64, that could specify flush what level TLB.
	 */
	if (mm_tlb_flush_nested(tlb->mm)) {
		/*
		 * The aarch64 yields better performance with fullmm by
		 * avoiding multiple CPUs spamming TLBI messages at the
		 * same time.
		 *
		 * On x86 non-fullmm doesn't yield significant difference
		 * against fullmm.
		 */
		tlb->fullmm = 1;
		__tlb_reset_range(tlb);
		tlb->freed_tables = 1;
	}

	tlb_flush_mmu(tlb);

#ifndef CONFIG_MMU_GATHER_NO_GATHER
	tlb_batch_list_free(tlb);
#endif
	dec_tlb_flush_pending(tlb->mm);
}